{
  "opencollection": "1.0.0",
  "info": {
    "name": "Hugging Face Dataset Viewer API",
    "version": "1.0.0"
  },
  "items": [
    {
      "info": {
        "name": "Dataset Info",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Check Dataset Validity",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://datasets-server.huggingface.co/is-valid",
            "params": [
              {
                "name": "dataset",
                "value": "cornell-movie-review-data/rotten_tomatoes",
                "type": "query",
                "description": "The dataset ID on the Hugging Face Hub"
              }
            ]
          },
          "docs": "Check whether a specific dataset is valid and processed by the Dataset Viewer. Returns availability status for preview, viewer, search, filter, and statistics features."
        },
        {
          "info": {
            "name": "Get Dataset Splits",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://datasets-server.huggingface.co/splits",
            "params": [
              {
                "name": "dataset",
                "value": "squad",
                "type": "query",
                "description": "The dataset ID on the Hugging Face Hub"
              }
            ]
          },
          "docs": "Get the list of subsets (configurations) and splits for a dataset. A dataset can have multiple subsets, each with different splits (e.g., train, test, validation)."
        }
      ]
    },
    {
      "info": {
        "name": "Data Access",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Get First Rows of a Split",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://datasets-server.huggingface.co/first-rows",
            "params": [
              {
                "name": "dataset",
                "value": "squad",
                "type": "query",
                "description": "The dataset ID"
              },
              {
                "name": "config",
                "value": "plain_text",
                "type": "query",
                "description": "The subset (configuration) name"
              },
              {
                "name": "split",
                "value": "train",
                "type": "query",
                "description": "The split name"
              }
            ]
          },
          "docs": "Get the first 100 rows of a dataset split. Useful for previewing data structure and content."
        },
        {
          "info": {
            "name": "Get a Slice of Rows",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://datasets-server.huggingface.co/rows",
            "params": [
              {
                "name": "dataset",
                "value": "squad",
                "type": "query",
                "description": "The dataset ID"
              },
              {
                "name": "config",
                "value": "plain_text",
                "type": "query",
                "description": "The subset (configuration) name"
              },
              {
                "name": "split",
                "value": "train",
                "type": "query",
                "description": "The split name"
              },
              {
                "name": "offset",
                "value": "10",
                "type": "query",
                "description": "Row offset to start from"
              },
              {
                "name": "length",
                "value": "10",
                "type": "query",
                "description": "Number of rows to return (max 100)"
              }
            ]
          },
          "docs": "Get a slice of rows from a dataset split with pagination support. Returns up to 100 rows per request."
        }
      ]
    },
    {
      "info": {
        "name": "Search & Filter",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Search Text in a Split",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://datasets-server.huggingface.co/search",
            "params": [
              {
                "name": "dataset",
                "value": "example_value",
                "type": "query",
                "description": "The dataset ID"
              },
              {
                "name": "config",
                "value": "example_value",
                "type": "query",
                "description": "The subset (configuration) name"
              },
              {
                "name": "split",
                "value": "example_value",
                "type": "query",
                "description": "The split name"
              },
              {
                "name": "query",
                "value": "machine learning",
                "type": "query",
                "description": "Search query string"
              },
              {
                "name": "offset",
                "value": "10",
                "type": "query"
              },
              {
                "name": "length",
                "value": "10",
                "type": "query"
              }
            ]
          },
          "docs": "Full-text search within a dataset split. Searches across all text columns and returns matching rows."
        },
        {
          "info": {
            "name": "Filter Rows in a Split",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://datasets-server.huggingface.co/filter",
            "params": [
              {
                "name": "dataset",
                "value": "example_value",
                "type": "query",
                "description": "The dataset ID"
              },
              {
                "name": "config",
                "value": "example_value",
                "type": "query",
                "description": "The subset (configuration) name"
              },
              {
                "name": "split",
                "value": "example_value",
                "type": "query",
                "description": "The split name"
              },
              {
                "name": "where",
                "value": "label = 1",
                "type": "query",
                "description": "SQL-like WHERE clause for filtering (e.g., \"label = 1\" or \"score > 0.5\")"
              },
              {
                "name": "orderby",
                "value": "score DESC",
                "type": "query",
                "description": "SQL-like ORDER BY clause for sorting"
              },
              {
                "name": "offset",
                "value": "10",
                "type": "query"
              },
              {
                "name": "length",
                "value": "10",
                "type": "query"
              }
            ]
          },
          "docs": "Filter rows in a dataset split using SQL-like WHERE and ORDER BY clauses. Supports comparison operators and logical operations."
        }
      ]
    },
    {
      "info": {
        "name": "Files & Metadata",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "List Parquet Files",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://datasets-server.huggingface.co/parquet",
            "params": [
              {
                "name": "dataset",
                "value": "squad",
                "type": "query",
                "description": "The dataset ID"
              }
            ]
          },
          "docs": "Get the list of a dataset's files converted to Parquet format. Datasets are auto-converted to Parquet on the Hub for efficient data access."
        },
        {
          "info": {
            "name": "Get Dataset Size",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://datasets-server.huggingface.co/size",
            "params": [
              {
                "name": "dataset",
                "value": "squad",
                "type": "query",
                "description": "The dataset ID"
              }
            ]
          },
          "docs": "Get size information for a dataset including the number of rows and size in bytes for the full dataset and for each subset and split."
        },
        {
          "info": {
            "name": "Get Dataset Statistics",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://datasets-server.huggingface.co/statistics",
            "params": [
              {
                "name": "dataset",
                "value": "example_value",
                "type": "query",
                "description": "The dataset ID"
              },
              {
                "name": "config",
                "value": "example_value",
                "type": "query",
                "description": "The subset (configuration) name"
              },
              {
                "name": "split",
                "value": "example_value",
                "type": "query",
                "description": "The split name"
              }
            ]
          },
          "docs": "Get descriptive statistics for columns in a dataset split including distributions, counts, means, and other summary metrics."
        },
        {
          "info": {
            "name": "Get Croissant Metadata",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://datasets-server.huggingface.co/croissant",
            "params": [
              {
                "name": "dataset",
                "value": "squad",
                "type": "query",
                "description": "The dataset ID"
              }
            ]
          },
          "docs": "Get Croissant (schema.org/Dataset compatible) metadata for a dataset. Croissant is a metadata format for ML datasets based on schema.org."
        }
      ]
    }
  ],
  "bundled": true
}